gemini-watermark-remover
rookie-ricardo/erduo-skills
Remove Gemini AI watermarks from images using reverse alpha blending.
What is gemini-watermark-remover?
Removes the visible Gemini watermark from the bottom-right corner of images using reverse alpha blending techniques. Use this when you need to strip watermarks from individual images, batch-process multiple Gemini-generated images, or build a CLI tool for watermark removal without server-side components.
- Detects and removes the Gemini AI watermark from image bottom-right corner
- Uses reverse alpha blending with pre-captured watermark alpha maps
- Processes images via command-line interface with flexible input/output formats
- Infers output image format automatically from file extension
- Provides algorithm documentation for customization and understanding detection rules
How to install gemini-watermark-remover
npx skills add https://github.com/rookie-ricardo/erduo-skills --skill gemini-watermark-remover- Python 3.9 or higher
- Pillow library (install via pip install -r requirements.txt)
How to use gemini-watermark-remover
- 1.Navigate to the skills folder: cd skills/gemini-watermark-remover/scripts
- 2.Install dependencies: pip install -r requirements.txt
- 3.Run the CLI with input and output paths: python remove_watermark.py <input-image> <output-image>
- 4.Check references/algorithm.md if you need to adjust detection rules or alpha blending logic
Use cases
- Remove watermarks from individual Gemini-generated images for personal use
- Batch-process multiple watermarked images in automated workflows
- Build or modify CLI scripts that integrate watermark removal into image pipelines
- Adjust detection rules or alpha blending logic for specific image types
- Developers building image processing tools
- Users needing to remove Gemini watermarks from generated images
- Teams automating batch image cleanup workflows
gemini-watermark-remover FAQ
Any format supported by Pillow (PNG, JPG, JPEG, BMP, GIF, etc.). Output format is automatically inferred from the output file extension.
The CLI processes one image at a time, but you can wrap it in a shell script or Python loop to batch-process multiple files.
Read references/algorithm.md to understand the detection rules and alpha blending logic, then adjust parameters in remove_watermark.py as needed.
No, it's a pure Python CLI tool that works entirely locally without server-side dependencies.
Full instructions (SKILL.md)
Source of truth, from rookie-ricardo/erduo-skills.
name: gemini-watermark-remover description: Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini watermark without HTML or server-side components.
Gemini Watermark Remover
Dependencies
- Python 3.9+
- Pillow (install with
pip install -r requirements.txt)
Quick start
- Install dependencies in the scripts folder:
cd skills/gemini-watermark-remover/scripts && pip install -r requirements.txt
- Run the CLI:
python remove_watermark.py <input-image> <output-image>
CLI usage
- Parameters:
input-image: path to the Gemini watermarked imageoutput-image: path for the cleaned image (format inferred from extension)
Example:
python remove_watermark.py ./in.png ./out.png
What this skill provides
scripts/remove_watermark.py: CLI entry point and core algorithm.assets/bg_48.png,assets/bg_96.png: Pre-captured watermark alpha maps.references/algorithm.md: Math, detection rules, and limits.
Workflow
- Use
remove_watermark.pyfor one-off processing. - If you need to adjust detection rules or alpha logic, read
references/algorithm.md.
Notes
- The script uses Pillow for image IO and per-pixel edits.
- Output format is inferred from the output file extension by Pillow.
Related skills
More from rookie-ricardo/erduo-skills and the wider catalog.
persistent-memory
ALWAYS USE THIS SKILL when handling persistent memory in this workspace, including task-start memory recall, explicit "remember" instructions, storing durable preferences/facts, and retrieving prior context. This skill owns the local memory workflow and CLI for init/sync/search/add/recent/stats.
asc-screenshot-resize
Resize and validate App Store screenshots with current asc screenshot-size data and macOS sips. Use when preparing or fixing screenshots for App Store Connect submission.
tutor
Interactive quiz tutor that tracks concept mastery and identifies knowledge gaps.
tutor-setup
Transform PDFs, code, or web sources into an interactive Obsidian StudyVault with practice questions and architecture guides.
app-planner
Plans new macOS apps or analyzes existing projects. Creates comprehensive planning documents covering architecture, features, UI/UX, and tech stack. Use when planning a new macOS app or auditing an existing one.
rsbuild-best-practices
Rsbuild configuration, optimization, and debugging best practices for production projects.